1 files changed, 127 insertions, 72 deletions

diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a2a407039227..b33c894b6cf3 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -21,6 +21,64 @@
 #include "xfs_ag_resv.h"
 
 /*
+ * Write new AG headers to disk. Non-transactional, but need to be
+ * written and completed prior to the growfs transaction being logged.
+ * To do this, we use a delayed write buffer list and wait for
+ * submission and IO completion of the list as a whole. This allows the
+ * IO subsystem to merge all the AG headers in a single AG into a single
+ * IO and hide most of the latency of the IO from us.
+ *
+ * This also means that if we get an error whilst building the buffer
+ * list to write, we can cancel the entire list without having written
+ * anything.
+ */
+static int
+xfs_resizefs_init_new_ags(
+	struct xfs_trans	*tp,
+	struct aghdr_init_data	*id,
+	xfs_agnumber_t		oagcount,
+	xfs_agnumber_t		nagcount,
+	xfs_rfsblock_t		delta,
+	bool			*lastag_extended)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	xfs_rfsblock_t		nb = mp->m_sb.sb_dblocks + delta;
+	int			error;
+
+	*lastag_extended = false;
+
+	INIT_LIST_HEAD(&id->buffer_list);
+	for (id->agno = nagcount - 1;
+	     id->agno >= oagcount;
+	     id->agno--, delta -= id->agsize) {
+
+		if (id->agno == nagcount - 1)
+			id->agsize = nb - (id->agno *
+					(xfs_rfsblock_t)mp->m_sb.sb_agblocks);
+		else
+			id->agsize = mp->m_sb.sb_agblocks;
+
+		error = xfs_ag_init_headers(mp, id);
+		if (error) {
+			xfs_buf_delwri_cancel(&id->buffer_list);
+			return error;
+		}
+	}
+
+	error = xfs_buf_delwri_submit(&id->buffer_list);
+	if (error)
+		return error;
+
+	xfs_trans_agblocks_delta(tp, id->nfree);
+
+	if (delta) {
+		*lastag_extended = true;
+		error = xfs_ag_extend_space(mp, tp, id, delta);
+	}
+	return error;
+}
+
+/*
  * growfs operations
  */
 static int
@@ -33,22 +91,25 @@ xfs_growfs_data_private(
 	xfs_agnumber_t		nagcount;
 	xfs_agnumber_t		nagimax = 0;
 	xfs_rfsblock_t		nb, nb_div, nb_mod;
-	xfs_rfsblock_t		delta;
+	int64_t			delta;
+	bool			lastag_extended;
 	xfs_agnumber_t		oagcount;
 	struct xfs_trans	*tp;
 	struct aghdr_init_data	id = {};
 
 	nb = in->newblocks;
-	if (nb < mp->m_sb.sb_dblocks)
-		return -EINVAL;
-	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
+	error = xfs_sb_validate_fsb_count(&mp->m_sb, nb);
+	if (error)
 		return error;
-	error = xfs_buf_read_uncached(mp->m_ddev_targp,
+
+	if (nb > mp->m_sb.sb_dblocks) {
+		error = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
 				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
-	if (error)
-		return error;
-	xfs_buf_relse(bp);
+		if (error)
+			return error;
+		xfs_buf_relse(bp);
+	}
 
 	nb_div = nb;
 	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
@@ -56,10 +117,16 @@ xfs_growfs_data_private(
 	if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
 		nagcount--;
 		nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks;
-		if (nb < mp->m_sb.sb_dblocks)
-			return -EINVAL;
 	}
 	delta = nb - mp->m_sb.sb_dblocks;
+	/*
+	 * Reject filesystems with a single AG because they are not
+	 * supported, and reject a shrink operation that would cause a
+	 * filesystem to become unsupported.
+	 */
+	if (delta < 0 && nagcount < 2)
+		return -EINVAL;
+
 	oagcount = mp->m_sb.sb_agcount;
 
 	/* allocate the new per-ag structures */
@@ -67,55 +134,34 @@ xfs_growfs_data_private(
 		error = xfs_initialize_perag(mp, nagcount, &nagimax);
 		if (error)
 			return error;
+	} else if (nagcount < oagcount) {
+		/* TODO: shrinking the entire AGs hasn't yet completed */
+		return -EINVAL;
 	}
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
-			XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+			(delta > 0 ? XFS_GROWFS_SPACE_RES(mp) : -delta), 0,
+			XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
 
-	/*
-	 * Write new AG headers to disk. Non-transactional, but need to be
-	 * written and completed prior to the growfs transaction being logged.
-	 * To do this, we use a delayed write buffer list and wait for
-	 * submission and IO completion of the list as a whole. This allows the
-	 * IO subsystem to merge all the AG headers in a single AG into a single
-	 * IO and hide most of the latency of the IO from us.
-	 *
-	 * This also means that if we get an error whilst building the buffer
-	 * list to write, we can cancel the entire list without having written
-	 * anything.
-	 */
-	INIT_LIST_HEAD(&id.buffer_list);
-	for (id.agno = nagcount - 1;
-	     id.agno >= oagcount;
-	     id.agno--, delta -= id.agsize) {
-
-		if (id.agno == nagcount - 1)
-			id.agsize = nb -
-				(id.agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
-		else
-			id.agsize = mp->m_sb.sb_agblocks;
+	if (delta > 0) {
+		error = xfs_resizefs_init_new_ags(tp, &id, oagcount, nagcount,
+						  delta, &lastag_extended);
+	} else {
+		static struct ratelimit_state shrink_warning = \
+			RATELIMIT_STATE_INIT("shrink_warning", 86400 * HZ, 1);
+		ratelimit_set_flags(&shrink_warning, RATELIMIT_MSG_ON_RELEASE);
 
-		error = xfs_ag_init_headers(mp, &id);
-		if (error) {
-			xfs_buf_delwri_cancel(&id.buffer_list);
-			goto out_trans_cancel;
-		}
+		if (__ratelimit(&shrink_warning))
+			xfs_alert(mp,
+	"EXPERIMENTAL online shrink feature in use. Use at your own risk!");
+
+		error = xfs_ag_shrink_space(mp, &tp, nagcount - 1, -delta);
 	}
-	error = xfs_buf_delwri_submit(&id.buffer_list);
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_trans_agblocks_delta(tp, id.nfree);
-
-	/* If there are new blocks in the old last AG, extend it. */
-	if (delta) {
-		error = xfs_ag_extend_space(mp, tp, &id, delta);
-		if (error)
-			goto out_trans_cancel;
-	}
-
 	/*
 	 * Update changed superblock fields transactionally. These are not
 	 * seen by the rest of the world until the transaction commit applies
@@ -123,11 +169,19 @@ xfs_growfs_data_private(
 	 */
 	if (nagcount > oagcount)
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount);
-	if (nb > mp->m_sb.sb_dblocks)
-		xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
-				 nb - mp->m_sb.sb_dblocks);
+	if (delta)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS, delta);
 	if (id.nfree)
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);
+
+	/*
+	 * Sync sb counters now to reflect the updated values. This is
+	 * particularly important for shrink because the write verifier
+	 * will fail if sb_fdblocks is ever larger than sb_dblocks.
+	 */
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+		xfs_log_sb(tp);
+
 	xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp);
 	if (error)
@@ -139,28 +193,29 @@ xfs_growfs_data_private(
 	xfs_set_low_space_thresholds(mp);
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 
-	/*
-	 * If we expanded the last AG, free the per-AG reservation
-	 * so we can reinitialize it with the new size.
-	 */
-	if (delta) {
-		struct xfs_perag	*pag;
-
-		pag = xfs_perag_get(mp, id.agno);
-		error = xfs_ag_resv_free(pag);
-		xfs_perag_put(pag);
-		if (error)
-			return error;
+	if (delta > 0) {
+		/*
+		 * If we expanded the last AG, free the per-AG reservation
+		 * so we can reinitialize it with the new size.
+		 */
+		if (lastag_extended) {
+			struct xfs_perag	*pag;
+
+			pag = xfs_perag_get(mp, id.agno);
+			error = xfs_ag_resv_free(pag);
+			xfs_perag_put(pag);
+			if (error)
+				return error;
+		}
+		/*
+		 * Reserve AG metadata blocks. ENOSPC here does not mean there
+		 * was a growfs failure, just that there still isn't space for
+		 * new user data after the grow has been run.
+		 */
+		error = xfs_fs_reserve_ag_blocks(mp);
+		if (error == -ENOSPC)
+			error = 0;
 	}
-
-	/*
-	 * Reserve AG metadata blocks. ENOSPC here does not mean there was a
-	 * growfs failure, just that there still isn't space for new user data
-	 * after the grow has been run.
-	 */
-	error = xfs_fs_reserve_ag_blocks(mp);
-	if (error == -ENOSPC)
-		error = 0;
 	return error;
 
 out_trans_cancel: